Downloads · 30 days
0
anliR1-gpt2-kd
asun17904/anliR1-gpt2-kd
anliR1-gpt2-kd is a machine learning model from asun17904. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
Access
Public
Updated Jan 30, 2024
Repo size
25.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin498 MB · 100%
At a glance
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Jan 28, 2024
- Updated
- Jan 30, 2024
- SHA
- 3111fa40
Model card
From the Hugging Face model README
Knowledge Continuity Regularized Network
Dataset: ANLI Round: None
Trainer Hyperparameters:
lr= 5e-05per_device_batch_size= 8gradient_accumulation_steps= 1weight_decay= 0.0seed= 42
Regularization Hyperparameters
numerical stability denominator constant= 0.01lambda= 0.001alpha= 2.0beta= 2.0
Extended Logs:
| eval_loss | eval_accuracy | epoch |
|---|---|---|
| 37.124 | 0.356 | 1.0 |
| 35.453 | 0.414 | 2.0 |
| 36.455 | 0.393 | 3.0 |
| 35.682 | 0.417 | 4.0 |
| 36.248 | 0.397 | 5.0 |
| 35.343 | 0.431 | 6.0 |
| 35.734 | 0.413 | 7.0 |
| 35.896 | 0.414 | 8.0 |
| 35.431 | 0.434 | 9.0 |
| 35.405 | 0.425 | 10.0 |
| 34.976 | 0.445 | 11.0 |
| 35.522 | 0.434 | 12.0 |
| 35.389 | 0.436 | 13.0 |
| 35.805 | 0.422 | 14.0 |
| 35.435 | 0.434 | 15.0 |
| 35.751 | 0.423 | 16.0 |
| 35.567 | 0.430 | 17.0 |
| 35.204 | 0.439 | 18.0 |
| 35.490 | 0.430 | 19.0 |
Test Accuracy: 0.430
- Library
- pytorch
- License
- mit
- Languages
- en
- Created
- Jan 28, 2024
- Updated
- Jan 30, 2024